Design and analysis of text document clustering using salp swarm algorithm

• Published in: The Journal of supercomputing Vol. 78; no. 14; pp. 16197 - 16213
• Main Authors: Ponnusamy, Muruganantham, Bedi, Pradeep, Suresh, Tamilarasi, Alagarsamy, Aravindhan, Manikandan, R., Yuvaraj, N.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2022; Springer Nature B.V
• Subjects: Algorithms; Clustering; Compilers; Computer Science; Distance measurement; Documents; Interpreters; Machine learning in Intelligent Autonomous Systems; Processor Architectures; Programming Languages; Similarity; Salp swarm optimization; Text documents; Document clustering
• ISSN: 0920-8542; 1573-0484
• DOI: 10.1007/s11227-022-04525-0

In the technological era, exponential increase of unorganized text documents offers increased difficulties retrieving the most relevant data. The document clustering is a most prominent technique that transforms unorganized contents into organized contents in the form of clusters. The recognition technique always undergoes clustering of text documents with misleading or redundant information that degrades document clustering quality. In this study, a salp swarm algorithm (SSA) is used for clustering the text documents. The study is improved with a similarity and a distance-based measurements as an objective function in the clustering domain. The experimental validation is conducted to show the efficacy of SSA-based similarity distance measurement that prominently improves the quality of clustering the text documents. The comparison with existing methods shows that the proposed SSA offers better clustering of text documents in accuracy, sensitivity, specificity, and f -measure.